Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

4o Image Generation

openai.com

Post reply on HN
Print view View original

231–240 of 629 posts

Re: 4o Image Generation

#231

Post by cruffle_duffle »

meeton wrote: post #185
jjbinx007 wrote: post #130

Earlier quoted context omitted.

It still can't generate a full glass of wine. Even in follow up questions it failed to manipulate the image correctly.

https://i.imgur.com/xsFKqsI.png "Draw a picture of a full glass of wine, ie a wine glass which is full to the brim with red wine and almost at the point of spilling over... Zoom out to show the full wine glass, and add a caption to the top which says "HELL YEAH". Keep the wine level of the glass exactly the same."

Maybe the "HELL YEAH" added a "party implication" which shifted it's "thinking" into just correct enough latent space that it was able to actually hunt down some image somewhere in its training data of a truly full glass of wine.

I almost wonder if prompting it "similar to a full glass of beer" would get it shifted just enough.

Re: 4o Image Generation

#232

Post by nerder92 »

SamBam wrote: post #230
blixt wrote: post #104

What's important about this new type of image generation that's happening with tokens rather than with diffusion, is that this is effectively reasoning in pixel space. Example: Ask it to draw a notepad with an empty tic-tac-toe, then tell it to make the first move, then you make a move, and so on. You can also do very impressive information-conserving translations, such as changing the drawing style, but also stuff l…

Hmmm, I wanted to do that tic tac toe example, and it failed to create a 3x3 grid, instead creating a 5x5 (?) grid with two first moves marked. https://chatgpt.com/share/67e32d47-eac0-8011-9118-51b81756ec...

I tried to play it, and while the conversation is right the image is just all wrong

Re: 4o Image Generation

#233

Post by roenxi »

kh_hk wrote: post #57

> Introducing 4o Image Generation: [...] our most advanced image generator yet Then google: > Gemini 2.5: Our most intelligent AI model > Introducing Gemini 2.0 | Our most capable AI model yet I could go on forever. I hope this trend dies and apple starts using something effective so all the other companies can start copying a new lexicon.

We're in the middle of a massive and unprecedented boom in AI capabilities. It is hard to be upset about this phrasing - it is literally true and extremely accurate.

Re: 4o Image Generation

#235

Post by Taek »

blixt wrote: post #104

What's important about this new type of image generation that's happening with tokens rather than with diffusion, is that this is effectively reasoning in pixel space. Example: Ask it to draw a notepad with an empty tic-tac-toe, then tell it to make the first move, then you make a move, and so on. You can also do very impressive information-conserving translations, such as changing the drawing style, but also stuff l…

> What's important about this new type of image generation that's happening with tokens rather than with diffusion, is that this is effectively reasoning in pixel space.

I do not think that this is correct. Prior to this release, 4o would generate images by calling out to a fully external model (DALL-E). After this release, 4o generates images by calling out to a multi-modal model that was trained alongside it.

You can ask 4o about this yourself. Here's what it said to me:

"So while I’m deeply multimodal in cognition (understanding and coordinating text + image), image generation is handled by a linked latent diffusion model, not an end-to-end token-unified architecture."

Re: 4o Image Generation

#236

Post by akomtu »

The real test for image generators is the image->text->image conversion. In other words it should be able to describe an image with words and then use the words to recreate the original image with a high accuracy. The text representation of the image doesn't have to be English. It can be a program, e.g. a shader, that draws the image. I believe in 5-10 years it will be possible to give this tool a picture of rainforest, tell it to write a shader that draws this forest, and tell it to add Avatar-style flying rocks. Instead of these silly benchmarks, we'll read headlines like "GenAI 5.1 creates a 3D animation of a photograph of the Niagara falls in 3 seconds, less than 4KB of code that runs at 60fps".

Re: 4o Image Generation

#237

Post by jorvi »

Loeffelmann wrote: post #142
minimaxir wrote: post #136

Earlier quoted context omitted.

That is an unexpectedly literal definition of "full glass".

That's the point. With the old models they all failed to produce a wine glass that is completley to the brim full. Because you can't find that a lot in the data they used for training.

The old models were doing it correct also.

There is no one correct way to interpert 'full'. If you go to a wine bar and ask for a full glass of wine, they'll probably interpert that as a double. But you could also interpert it the way a friend would at home, which is about 2-3cm from the rim.

Personally I would call a glass of wine filled to the brim 'overfilled', not 'full'.

Re: 4o Image Generation

#238

Post by M4v3R »

swyx wrote: post #228
M4v3R wrote: post #170

I’ve just tried it and oh wow it’s really good. I managed to create a birthday invitation card for my daughter in basically 1-shot, it nailed exactly the elements and style I wanted. Then I asked to retain everything but tweak the text to add more details about the date, venue etc. And it did. I’m in shock. Previous models would not be even halfway there.

share prompt minus identifying details?

> Draw a birthday invitation for a 4 year old girl [name here]. It should be whimsical, look like its hand-drawn with little drawings on the sides of stuff like dinosaurs, flowers, hearts, cats. The background should be light and the foreground elements should be red, pink, orange and blue.

Then I asked for some changes:

> That's almost perfect! Retain this style and the elements, but adjust the text to read:

> [refined text]

> And then below it should add the location and date details:

> [location details]

Re: 4o Image Generation

#239

Post by drdeca »

jorvi wrote: post #237
Loeffelmann wrote: post #142

Earlier quoted context omitted.

That's the point. With the old models they all failed to produce a wine glass that is completley to the brim full. Because you can't find that a lot in the data they used for training.

The old models were doing it correct also. There is no one correct way to interpert 'full'. If you go to a wine bar and ask for a full glass of wine, they'll probably interpert that as a double. But you could also interpert it the way a friend would at home, which is about 2-3cm from the rim. Personally I would call a glass of wine filled to the brim 'overfilled', not 'full'.

People were telling the models explicitly to fill it to the brim, and the models were still producing images where it was filled to approximately the half-way point.

Re: 4o Image Generation

#240

Post by astrange »

lyu07282 wrote: post #218
xg15 wrote: post #162

Earlier quoted context omitted.

> What's important about this new type of image generation that's happening with tokens rather than with diffusion That sounds really interesting. Are there any write-ups how exactly this works?

Would be interested to know as well. As far as I know there is no public information about how this works exactly. This is all I could find: > The system uses an autoregressive approach — generating images sequentially from left to right and top to bottom, similar to how text is written — rather than the diffusion model technique used by most image generators (like DALL-E) that create the entire image at once. Goh sp…

DALL-E was an autoregressive encoder; it's 2 and 3 that used diffusion and were much less intelligent as a result.
Post reply on HN